Hierarchical World Models as Visual Whole-Body Humanoid Controllers
Lists
Only you see this
Abstract
Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both of which are trained with rewards. Our approach produces highly performant control policies in 8 tasks with a simulated 56-DoF humanoid, while synthesizing motions that are broadly preferred by humans. Code and videos: https://rlpuppeteer.github.io
BibTeX
@inproceedings{hansen2025hierarchical,
author = {Nicklas Hansen and Jyothir S V and Vlad Sobal and Yann LeCun and Xiaolong Wang and Hao Su},
title = {{Hierarchical World Models as Visual Whole-Body Humanoid Controllers}},
booktitle = {International Conference on Learning Representations},
year = {2025},
url = {https://openreview.net/forum?id=7wuJMvK639},
}